Models

← All models

Hermes 3 Llama 3.1 405B

Nous Research · 2024-08-13 · 405.9B parameters

Hermes 3 Llama 3.1 405B is Nous Research's first full-parameter fine-tune of Meta's Llama 3.1 405B, released in August 2024. It was fine-tuned on an approximately 390-million-token instruction dataset with primarily synthetically generated responses, retains the base model's 131,072-token context window, and adds agentic function calling and structured outputs. Because the dataset size is approximate and the base model's cumulative pretraining exposure is not exact, no exact training-token count is recorded.

Benchmark scores